Developing a seq2seq neural network using visual attention to transform mathematical expressions from images to LaTeX.
The paper presents the methods of development and the results of research on the effectiveness of the seq2seq neural network architecture using Visual Attention mechanism to solve the im2latex problem. The essence of the task is to create a neural network capable of converting an image with mathemat...
Main Authors: | P. A. Vyaznikov, I. D. Kotilevets |
---|---|
Format: | Article |
Language: | Russian |
Published: |
Educational institution «Belarusian State University of Informatics and Radioelectronics»
2022-01-01
|
Series: | Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki |
Subjects: | |
Online Access: | https://doklady.bsuir.by/jour/article/view/3243 |
Similar Items
-
Novel Feature Extraction Method for Detecting Malicious MQTT Traffic Using Seq2Seq
by: Sunoh Choi, et al.
Published: (2022-12-01) -
Improving Text Summarization Quality by Combining T5-Based Models and Convolutional Seq2Seq Models
by: Arif Ridho Lubis, et al.
Published: (2023-12-01) -
Sentence‐Chain Based Seq2seq Model for Corpus Expansion
by: Euisok Chung, et al.
Published: (2017-08-01) -
Research on Short-Term Load Prediction Based on Seq2seq Model
by: Gangjun Gong, et al.
Published: (2019-08-01) -
WiFi Based Fingerprinting Positioning Based on Seq2seq Model
by: Haotai Sun, et al.
Published: (2020-07-01)